AutoML 2017
Automatic Machine Learning

Table of Contents

Preface

Invited Talk Abstracts

• Stochastic Gradient Descent: Going as Fast as Possible but not Faster 1-1
  Michele Sebag

Technical Papers

• Bayesian Optimization Combined with Incremental Evaluation for Neural Network Architecture Optimization 2-11
  Martin Wistuba
• Towards Automated Relational Data Wrangling 12-20
  Gust Verbruggen, Luc de Raedt
• autoBagging: Learning to Rank Bagging Workflows with Metalearning 21-27
  Fábio Pinto, Vitor Cerqueira, Carlos Soares, João Mendes-Moreira
• A Meta-Learning Approach to One-Step Active-Learning 28-40
  Gabriella Contardo, Ludovic Denoyer, Thierry Artieres
• Incremental Training of Deep Convolutional Neural Networks 41-48
  Roxana Istrate, Cristiano Malossi, Costas Bekas, Dimitrios Nikolopoulos
• Layered TPOT: Speeding up Tree-based Pipeline Optimization 49-68
  Pieter Gijsbers, Joaquin Vanschoren, Randal Olson
• Combining Feature and Algorithm Hyperparameter Selection using some Metalearning Methods 69-83
  Miguel Cachada, Salisu Abdulrahman, Pavel Brazdil
• Effect of Metalearning on Feature Selection Employment 84-90
  Silvia Nunes Das Dôres, Carlos Soares, Duncan Ruiz
• An Empirical Study of Hyperparameter Importance Across Datasets 91-98
  Jan van Rijn, Frank Hutter

Abstracts

• Meta-learning System for Automated Clustering 99-101
  Sergey Muravyov, Andrey Filchenkov
• NDSE: Instance Generation for Classification by Given Meta-Feature Description 102-104
  Alexey Zabashta, Andrey Filchenkov